Hi Sean,

Sorry for the delay on this. It looks like there was a bug in the handling of the subset command in moPrep(). In the latest development version, it should be fixed. You can find that, along with installation instructions here:

As an example, you can do the following:

library(Amelia)

data(africa)

mo.out <- moPrep(africa, trade ~ trade, subset = trade > 50)

a.out <- amelia(mo.out, cs = "country")

That should perform the type of subset analysis you were trying to do, at least in the development version.

Hope that helps!

Cheers,

Matt

~~~~~~~~~~~

Matthew Blackwell

Assistant Professor of Government

Harvard University

url: http://www.mattblackwell.org

On Wed, Sep 9, 2015 at 11:00 AM Sean Kates <sk5350@nyu.edu> wrote:

I've been attempting to work with Amelia to multiply overimpute values for a specific variable that have been measured with error. I know which observations were measured with error (they all have a value in a particular range) but I cannot use moPrep to properly prepare the data for overimputation. I want to use the "subset" and "gold.standard" arguments, but depending on how I write these, some error is always returned.

I cannot find a simple example of sample code that uses this means of prepping the data, rather than specifying the error proportion or sd (which I don't have/know). Can you either point me to an example, or suggest a simple line of code, using the following setup:

dataframe= data
variable with error: A
subset with error: where A<5

Thanks for any help or guidance you can give. All the best,

Sean
--
Amelia mailing list served by HUIT
[Un]Subscribe/View Archive: http://lists.gking.harvard.edu/?info=amelia
More info about Amelia: http://gking.harvard.edu/amelia
Amelia mailing list
Amelia@lists.gking.harvard.edu

To unsubscribe from this list or get other information:

https://lists.gking.harvard.edu/mailman/listinfo/amelia